Development of a Pedestrian Collision Avoidance System for Connected and Autonomous Vehicles With Cooperative Perception

Yang, Di; Taherpour, Abolfazl; Jeihani, Mansoureh; Cheng, Lei; Yang, Terry

i

Development of a Pedestrian Collision Avoidance System for Connected and Autonomous Vehicles With Cooperative Perception

2025-10-31
By Yang, Di ; Taherpour, Abolfazl ; Jeihani, Mansoureh ; ...

File Language:

English

Details

Creators:

Yang, Di ; Taherpour, Abolfazl ; Jeihani, Mansoureh ; Cheng, Lei ; Yang, Terry
Corporate Creators:

Morgan State University. Safety and Mobility Advancements Regional Transportation and Economics Research Center
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
Subject/TRT Terms:

Automated Vehicle Control Autonomous Vehicles Cameras Cooperation Cooperative Perception Crashes Infrastructure Laser Radar Pedestrians Pedestrian Safety Urban Transportation Vehicle To Everything Communications
Publication/ Report Number:

SM21
Resource Type:

Tech Report
Geographical Coverage:

United States
Edition:

Final Report
Corporate Publisher:

Morgan State University. Sustainable Mobility and Accessibility Regional Transportation Equity Research Center (SMARTER) Region 3 University Transportation Center (UTC)
Abstract:

Pedestrian safety remains a major challenge in urban transportation, especially when connected and automated vehicles (CAVs) must operate under occlusion, limited line-of-sight, and unpredictable pedestrian behavior. Pedestrians hidden by parked vehicles, roadside obstacles, or complex roadway geometry may not be detected in time by onboard sensors alone, leaving insufficient time for safe braking or maneuvering. To address this limitation, a cooperative perception (CP)-enabled pedestrian collision avoidance framework is developed by integrating roadside sensing, onboard sensing, multi-sensor fusion, edge computing, and Vehicle-to-Everything (V2X) communication. A camera-LiDAR fusion pipeline is established to provide reliable object detection and unified outputs for pedestrians and vehicles by combining the semantic strengths of cameras with the geometric accuracy of LiDAR. Controlled demonstrations using a Level 4 CAV platform in an occluded pedestrian-crossing scenario show that infrastructure-assisted CP can provide early warning for hidden pedestrians and enable safe stopping, whereas onboard sensing alone may detect the pedestrian too late. The results demonstrate the feasibility and safety value of CP for pedestrian protection and support its future integration into the Morgan State University SMART Corridor as a broader infrastructure-assisted safety framework for connected urban transportation systems.
Format:

PDF
Funding:

69A3552348303
Collection(s):

Autonomous Vehicles University Transportation Centers
Main Document Checksum:

urn:sha-512:efd0472676382eeb151ee0066ed64b5cc1b0f8f5f20828b5fdbd25b542118be6537f5d5b8336388042f20ae3ea34625fef6bf37ea5ba247f63dad546ef0dec02
Download URL:

https://rosap.ntl.bts.gov/view/dot/92777/dot_92777_DS1.pdf
File Type:

[PDF - 2.65 MB ]

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.